Article
Physics, Multidisciplinary
Huaiqian Bao, Zhaoting Shi, Jinrui Wang, Zongzhen Zhang, Guowei Zhang
Summary: A novel fault diagnosis method based on the GMNSF model is proposed in this paper, aiming to improve diagnostic performance by extracting sparse features from acoustic signals, and categorizing the results into different fault types.
Article
Computer Science, Artificial Intelligence
Shanshan Ji, Baokun Han, Zongzhen Zhang, Jinrui Wang, Bo Lu, Jiawei Yang, Xingxing Jiang
Summary: This study proposed a novel fault diagnosis method based on parallel sparse filtering for sparse feature extraction from acoustic signals, utilizing Z-score normalization to activate data. The results demonstrated the method's effectiveness in accurately extracting useful features for mechanical fault diagnosis.
Article
Chemistry, Multidisciplinary
Jiantao Lu, Weiwei Qian, Shunming Li, Rongqing Cui
Summary: A new intelligent fault diagnosis method of rotating machinery is proposed based on enhanced KNN, which combines parameter-based and case-based methods effectively. The method includes a dimension-reduction stage using sparse filtering for feature extraction, and a case-based reconstruction algorithm to adaptively determine the nearest neighbors for different testing samples. Experimental results on vibration signal datasets of bearings validate the effectiveness of the proposed method.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Zhiqiang Zhang, Qingyu Yang
Summary: The article introduces an intelligent fault diagnosis method based on reconstruction sparse filtering (RSF), which extracts diverse features by constraining the basis vectors, enabling precise description of the health conditions of rotating machinery and achieving significant performance improvement.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Baokun Han, Shanshan Ji, Jinrui Wang, Huaiqian Bao, Xingxing Jiang
Summary: A new intelligent fault diagnosis method based on deep learning is proposed in this paper, which uses sparse filtering and batch normalization techniques to address the impact of speed fluctuation on fault diagnosis. The effectiveness and superiority of the method are verified through experiments.
Article
Engineering, Mechanical
Zhongwei Zhang, Mingyu Shao, Chicheng Ma, Zhe Lv, Jilei Zhou
Summary: In this study, a novel domain adaptation approach is proposed for fault diagnosis of rotating machinery. The approach utilizes a deep sparse filtering model to extract fault features and a domain classifier to perform domain shift, while Z-score standardization and CORAL are employed as preprocessing tools. The effectiveness of the approach is verified through experimental vibration data from a bearing and a gear dataset.
NONLINEAR DYNAMICS
(2022)
Article
Automation & Control Systems
Guowei Zhang, Xianguang Kong, Jingli Du, Jinrui Wang, Shengkang Yang, Hongbo Ma
Summary: This study proposes an intelligent fault diagnosis method based on sparse feature learning, called adaptive multispace adjustable sparse filtering (AMSASF). The method automatically captures rich and complementary features under multiple spaces using multispace sparse filtering and improves the robustness of the algorithm by adaptively assigning different importance to different sparse spaces using attention mechanism. The sparsity is adjusted to increase the inter-class distance and obtain more discriminative features.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Mechanical
Zhiqiang Zhang, Shuiqing Xu, Hongtian Chen
Summary: Representation learning has powerful potential in intelligent fault diagnosis of rotating machinery. However, current sparse filtering-based methods have limitations in handling complex signals and selecting relevant features for fault classification. To address these issues, label-induced sparse filtering (LISF) is proposed, which utilizes discriminant information from labels and measures feature importance with a projection matrix. Experimental results demonstrate the effectiveness of LISF in learning discriminative features and achieving excellent diagnosis results. Moreover, LISF can automatically select key features for fault classification, improving diagnosis efficiency.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Chemistry, Analytical
Guocai Nie, Zhongwei Zhang, Mingyu Shao, Zonghao Jiao, Youjia Li, Lei Li
Summary: Recently, deep learning methods in fault diagnosis have been limited by their reliance on large amounts of labeled data, resulting in poor generalization ability. To address this, this paper proposes a generalized model based on self-supervised learning and sparse filtering (GSLSF). The method includes two stages: designing self-supervised learning pretext tasks and pseudo-labels based on fault and working condition information, and establishing a pre-trained model using sparse filtering. Then, a knowledge transfer mechanism and softmax regression are utilized to extract fault features and classify failures. The method significantly improves diagnostic performance and generalization ability with limited training data, as demonstrated by the results on two bearing datasets.
Article
Automation & Control Systems
Zhiqiang Zhang, Qingyu Yang, Zongze Wu
Summary: In this work, a novel RL method named sparse filtering with adaptive basis weighting (SFABW) is proposed to address the deficiencies of existing methods in intelligent fault diagnosis. By utilizing a three-layer neural network architecture and optimizing the entire network, a group of more effective bases with their weights are obtained simultaneously. Experimental results on motor bearing and gear datasets have demonstrated the effectiveness of this method.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Article
Automation & Control Systems
Yunhan Ling, Dianyu Fu, Peng Jiang, Yong Sun, Chao Yuan, Dali Huang, Jingfeng Lu, Siliang Lu
Summary: This study proposes an enhanced sparse filtering (ESF) method for mining and fusing machine signals' features for fault diagnosis. It utilizes a dimension reduction algorithm to obtain principal components of vibration signals, which are then exploited using sparse filtering (SF). The obtained features are combined as inputs for a softmax classifier to recognize machine fault patterns. The effectiveness and superiority of the proposed ESF method are validated using simulated and practical fault signals, confirming its potential for accurate and efficient rotation machine fault diagnosis.
TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL
(2023)
Article
Engineering, Multidisciplinary
Yang Liu, Weigang Wen, Yihao Bai, Qingzhou Meng
Summary: Data-driven intelligent fault diagnosis requires a large amount of labeled data, which is challenging to collect due to the limitations of operating mechanical devices under fault conditions for a long time. Additionally, the changing working conditions of rotating machinery make fault diagnosis difficult. This paper proposes a self-supervised Contrastive Learning model that combines Frequency-domain and Time-domain information (CLFT) for pre-training, which reduces the reliance on training data. Based on CLFT, a two-stage fault diagnosis pipeline for rotating machinery is developed, incorporating pre-training and fine-tuning strategies to accomplish specific diagnostic tasks. Experimental results demonstrate that CLFT effectively extracts generalization features from unlabeled vibration signals, enabling the fault diagnosis method to perform well with limited samples and variable working conditions.
Article
Computer Science, Artificial Intelligence
Zhiqiang Zhang, Qingyu Yang, Yanyang Zi
Summary: Representation learning has gained attention in intelligent fault diagnosis for automatically learning useful features. This paper introduces a simple and effective RL method called MSMPSF, which enhances fault information capture and feature representation richness through multi-scale fusion and multi-pooling fusion mechanisms. Experimental results demonstrate significant improvement in diagnosis performance, with reliable and competitive results compared to existing works.
Article
Engineering, Multidisciplinary
Pengxin Wang, Liuyang Song, Huaqing Wang, Changkun Han, Xudong Guo, Lingli Cui
Summary: Convolutional neural networks (CNNs) are important for health monitoring of industrial equipment, but pooling operations in a typical CNN can cause loss of impulse features. This paper proposes the Grouping Sparse Filtering (GSF) method to overcome this issue. GSF splits and filters the feature channels to preserve impulse features. Experimental results show that the 1D-CNN with GSF performs better in retaining impulse features and fault identification accuracy.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2022)
Article
Engineering, Multidisciplinary
Jing Yang, Yingqing Guo, Wanli Zhao
Summary: Electromechanical actuators (EMAs) have a significant impact on the safety of aircraft as the new generation of actuators. A semi-supervised sparse auto-encoder (SSAE) is employed to prune observed data and improve fault isolation accuracy, while a multi-channel long short-term network is used to explore temporal and spatial relationships for fault detection and isolation. Verification results confirm the effectiveness of the proposed method in diagnosing EMA faults.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2021)
Article
Engineering, Multidisciplinary
Weiwei Qian, Shunming Li, Jinrui Wang, Zenghui An, Xingxing Jiang
MEASUREMENT SCIENCE AND TECHNOLOGY
(2018)
Article
Metallurgy & Metallurgical Engineering
Li Shun-ming, Wang Jin-rui, Li Xiang-lian
JOURNAL OF CENTRAL SOUTH UNIVERSITY
(2018)
Article
Engineering, Multidisciplinary
Jinrui Wang, Shunming Li, Baokun Han, Zenghui An, Yu Xin, Weiwei Qian, Qijun Wu
MEASUREMENT SCIENCE AND TECHNOLOGY
(2019)
Article
Computer Science, Artificial Intelligence
Jinrui Wang, Shunming Li, Zenghui An, Xingxing Jiang, Weiwei Qian, Shanshan Ji
Article
Engineering, Multidisciplinary
Kun Xu, Shunming Li, Jinrui Wang, Zenghui An, Weiwei Qian, Huijie Ma
MEASUREMENT SCIENCE AND TECHNOLOGY
(2019)
Article
Engineering, Mechanical
Zongzhen Zhang, Shunming Li, Jinrui Wang, Yu Xin, Zenghui An
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2019)
Article
Engineering, Mechanical
Kun Xu, Shunming Li, Jinrui Wang, Zenghui An, Yu Xin
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING
(2020)
Article
Engineering, Mechanical
Yu Xin, Shunming Li, Jinrui Wang
JOURNAL OF VIBRATION ENGINEERING & TECHNOLOGIES
(2019)
Article
Computer Science, Artificial Intelligence
Zenghui An, Shunming Li, Jinrui Wang, Yu Xin, Kun Xu
Article
Automation & Control Systems
Zenghui An, Shunming Li, Jinrui Wang, Xingxing Jiang
Article
Computer Science, Artificial Intelligence
Kun Xu, Shunming Li, Xingxing Jiang, Zenghui An, Jinrui Wang, Tianyi Yu
Article
Computer Science, Artificial Intelligence
Zhongwei Zhang, Huaihai Chen, Shunming Li, Zenghui An, Jinrui Wang
Article
Computer Science, Information Systems
Yu Xin, Shunming Li, Zongzhen Zhang
Article
Engineering, Mechanical
Jinrui Wang, Shunming Li, Yu Xin, Zenghui An
JOURNAL OF VIBRATION ENGINEERING & TECHNOLOGIES
(2019)